Module 13: Researcher, Analyst, and Microsoft-Built Agents
Lesson 13.4: Getting Started with Analyst
Lesson Promise
Use Analyst for data-analysis reports while keeping file selection, assumptions, calculations, and human review visible.
Real-World Scenario
An operations director wants to compare sales performance across regions and quarters from several spreadsheets and CSV files.
Core Concept
Microsoft describes Analyst as an AI-powered assistant for data analysis that can work with attached data, calculate statistics, identify trends, show outliers, and produce readable reports with charts or tables.
Analyst is found under Agents where enabled, and administrators may need to enable it. Availability and file behavior can vary.
Analyst output should separate observed data, assumptions, methods, confidence, and recommendations. It should not become an unchecked executive decision.
Step-By-Step Workflow
- Choose approved data files and verify they are safe to attach.
- Ask one precise analysis question.
- Request methods, assumptions, charts, outliers, and confidence level.
- Ask for data quality concerns and missing fields.
- Verify at least one statistic or chart manually.
- Convert findings into a reviewed executive note.
Prompt Lab
Bad Prompt
Analyze these files.
Better Prompt
Compare sales by region and quarter, identify trends and outliers, and show assumptions and verification steps.
Expert Prompt
Use Analyst to create a data-analysis report from the approved files. Compare region, quarter, product, and channel. Include key trends, outliers, charts or tables, methods used, assumptions, data quality concerns, confidence level, manual verification checks, and questions for the data owner.
Hands-On Exercise
Design an Analyst prompt for a safe sample dataset and list three manual checks.
Deliverable
An Analyst prompt, report review checklist, and executive-summary template.
Agent Selection Review Checklist
Common Mistakes
- Using an agent because it sounds advanced instead of matching the task to the right tool.
- Treating Researcher reports, Analyst reports, or agent answers as final without reviewing sources, assumptions, and limits.
- Attaching sensitive data to an agent before checking purpose, permissions, and governance.
- Confusing built-in agents, organization-installed agents, Agent Builder agents, and Copilot Studio agents.
- Promising agent availability before checking license, admin approval, tenant controls, language, platform, and rollout.
Quiz / Checkpoint
What must you verify after an Analyst report?
The source files, data quality, calculations, assumptions, charts, outliers, and conclusions.
Official Sources To Verify
- Get started with agents in the Microsoft 365 Copilot app
- Get more agents in the Microsoft 365 Copilot app
- Get started with Researcher in Microsoft 365 Copilot
- Get started with Analyst in Microsoft 365 Copilot
- Build your own agent with Microsoft 365 Copilot
- Agent Builder in Microsoft 365 Copilot
- Build agents by using Agent Builder in Microsoft 365 Copilot
- Microsoft 365 Copilot Chat overview
- What Copilot license do I have
Want your AI product explained to a large AI-native audience?
Kingy AI helps AI companies turn complex products into clear, useful YouTube videos that drive awareness, product understanding, demos, clicks, and search visibility.
